Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -1.08
    ModLoader
    -0.88
    theless
    -0.81
    âĶĢâĶĢ
    -0.71
    ãĤ¸
    -0.68
    LCS
    -0.66
    UTERS
    -0.66
     FANTASY
    -0.65
    tumblr
    -0.65
    LEASE
    -0.64
    POSITIVE LOGITS
    zen
    0.88
    lett
    0.87
    inski
    0.83
    mann
    0.83
    strom
    0.82
    z
    0.81
    stad
    0.81
    beck
    0.81
    ham
    0.80
    itz
    0.78
    Act Density 0.514%

    No Known Activations